Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0805. Min Range: -6.0805
Max Act: 6.0805. Min Act: -0.1700
Data Index: 534471 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0805. Min Range: -6.0805
Max Act: 6.0180. Min Act: -0.1700
Data Index: 5364450 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9867. Min Act: -0.1700
Data Index: 3390861 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.8930. Min Act: -0.1700
Data Index: 1722761 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7992. Min Act: -0.1700
Data Index: 4996461 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7680. Min Act: -0.1700
Data Index: 45628 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7680. Min Act: -0.1700
Data Index: 7953160 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7367. Min Act: -0.1700
Data Index: 757095 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2698480 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7367. Min Act: -0.1700
Data Index: 7510238 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7055. Min Act: -0.1700
Data Index: 8792260 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7055. Min Act: -0.1700
Data Index: 7235196 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7055. Min Act: -0.1700
Data Index: 4757595 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2139106 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6430. Min Act: -0.1700
Data Index: 3417208 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6742. Min Act: -0.1700
Data Index: 2518452 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6742. Min Act: -0.1700
Data Index: 3419067 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6742. Min Act: -0.1700
Data Index: 8805618 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6742. Min Act: -0.1700
Data Index: 44171 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6742. Min Act: -0.1700
Data Index: 4657729 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19